Remix.run Logo
aliasxneo 4 hours ago

I don't really use our Google Home devices, but my wife does. Ever since the "update" I've noticed now that Gemini likes to ask her 2-3 follow up questions after each query. The first might be something like, "Would you like to know more about <X>?" My wife would answer "No" and Gemini would respond like, "Is there anything else you would like to discuss on the subject of <X>?" It's gotten to the point where she will start yelling "cancel" and "stop" to get it to shut up.

delichon 4 hours ago | parent [-]

I talk to chatbots while doing yardwork, often with both hands full. Yesterday I tried to get it to shut up mid conversation and just could not do it with voice only. I had to wait through several minutes of blathering, restarted by every random noise, before I could put the chainsaw down and turn it off.

I was amazed at my own level of anger at that. It was just a voice in my ears but I reacted to it viscerally like it was an assault. It didn't help that it was in the middle of a sequence of it telling one lie after another, like "yes, I can disconnect this conversation." Maybe what I had is a natural reaction to having a lying clueless asshole refuse to go away or shut up, which I haven't otherwise had to deal with lately.

dminik 4 hours ago | parent | next [-]

This is kind of funny, but very much expected.

The interface into the LLM is tokens in and out (text, images, audio). And the harness generally doesn't understand what you're passing in. The LLM has nothing to do other than to respond with tokens and empty responses (eg. just a stop token) have been aggressively trained out of it.

aNapierkowski 3 hours ago | parent | prev [-]

i know it "has" to respond the way its set up but it feels like a robot trying to get the last word when youre just trying to stop it